INDEX

Explanations

specific acronyms or initialisms

oai_token-act-pair · gpt-3.5-turbo

identifiers or acronyms related to entities or organizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

taboola

-0.83

ItemTracker

-0.71

licted

-0.66

alam

-0.62

jar

-0.61

give

-0.60

ighton

-0.60

spe

-0.59

scl

-0.57

 glowing

-0.57

POSITIVE LOGITS

ELS

1.12

ATA

1.11

AR

1.10

OT

1.10

OPS

1.08

ETS

1.07

OSS

1.07

ARE

1.06

ITION

1.05

KA

1.05

Activations Density 0.158%

specific acronyms or initialisms

identifiers or acronyms related to entities or organizations

No Comments

No Known Activations